mlsanityData to 7 Oct 2026

Variational Inference for Longitudinal Data Using Normalizing Flows

arXiv 2303.14220 ↗First posted 24 Mar 2023stat.ML cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper introduces a new latent variable generative model able to handle high dimensional longitudinal data and relying on variational inference. The time dependency between the observations of an input sequence is modelled using normalizing flows over the associated latent variables. The proposed method can be used to generate either fully synthetic longitudinal sequences or trajectories that are conditioned on several data in a sequence and demonstrates good robustness properties to missing data. We test the model on 6 datasets of different complexity and show that it can achieve better likelihood estimates than some competitors as well as more reliable missing data imputation. A code is made available at urlhttps://github.com/clementchadebec/variationalinferenceforlongitudinaldata.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 45 of its 83 references that are in the map. First posted on arXiv 24 Mar 2023.

Builds on

45 of 83 references.

References · 45

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018Neural Ordinary Differential Equationscited by 3,733
  3. 2015Variational Inference with Normalizing Flowscited by 2,161
  4. 2016Density estimation using Real NVPcited by 2,029
  5. 2016Variational Inference: A Review for Statisticianscited by 1,466
  6. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  7. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  8. 2017Masked Autoregressive Flow for Density Estimationcited by 680
  9. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  10. 2018Disentangling by Factorisingcited by 614
  11. 2015Importance Weighted Autoencoderscited by 454
  12. 2019Augmented Neural ODEscited by 396
33 more
  1. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
  2. 2018Understanding disentangling in β-VAEcited by 332
  3. 2015MADE: Masked Autoencoder for Distribution Estimationcited by 306
  4. 2018BRITS: Bidirectional Recurrent Imputation for Time Seriescited by 288
  5. 2017VAE with a VampPriorcited by 247
  6. 2016Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoderscited by 219
  7. 2018Hyperspherical Variational Auto-Encoderscited by 188
  8. 2016Variational Lossy Autoencodercited by 175
  9. 2016A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialoguescited by 174
  10. 2019GP-VAE: Deep Probabilistic Time Series Imputationcited by 171
  11. 2017Latent Space Oddity: on the Curvature of Deep Generative Modelscited by 169
  12. 2019Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limitcited by 168
  13. 2020Dissecting Neural ODEscited by 150
  14. 2018Disentangled Sequential Autoencodercited by 117
  15. 2019Continuous Hierarchical Representations with Poincar'e Variational Auto-Encoderscited by 111
  16. 2020Learning Latent Space Energy-Based Prior Modelcited by 104
  17. 2017The Riemannian Geometry of Deep Generative Modelscited by 81
  18. 2018Gaussian Process Prior Variational Autoencoderscited by 72
  19. 2018Explorations in Homeomorphic Variational Auto-Encodingcited by 65
  20. 2017Metrics for Deep Generative Modelscited by 53
  21. 2018Hamiltonian Variational Auto-Encodercited by 41
  22. 2021Learning Dynamic Alignment via Meta-filter for Few-shot Learningcited by 41
  23. 2020Vid-ODE: Continuous-Time Video Generation with Neural Ordinary Differential Equationcited by 39
  24. 2020Variational Autoencoders with Riemannian Brownian Motion Priorscited by 34
  25. 2020Longitudinal Self-Supervised Learningcited by 30
  26. 2021Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencodercited by 27
  27. 2022Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Casecited by 26
  28. 2020Longitudinal Variational Autoencodercited by 25
  29. 2022A Geometric Perspective on Variational Autoencoderscited by 24
  30. 2018High-Resolution Mammogram Synthesis using Progressive Generative Adversarial Networkscited by 10
  31. 2021Simple Video Generation using Neural ODEscited by 9
  32. 2018Learning distributions of shape trajectories from longitudinal datasets: a hierarchical model on a manifold of diffeomorphismscited by 8
  33. 2017Statistical learning of spatiotemporal patterns from longitudinal manifold-valued networkscited by 3

Built on by

Not cited yet.